Designing a 3D modeled object via user-interaction

E Mehr - US Patent 11,556,678, 2023 - Google Patents
(57) ABSTRACT A computer-implemented method for designing a 3D modeled object via
user-interaction. The method includes obtaining the 3D modeled object and a machine …

Neural network verification based on cognitive trajectories

JF Leon, JS Turek, DIG Aguirre, IJ Alvarez… - US Patent …, 2024 - Google Patents
Abstract Systems, apparatuses and methods may provide for technology that identifies a
cognitive space that is to be a compressed representation of activations of a neural network …

Object classification exception handling via machine learning

AV Wozniak, DP Smart - US Patent 11,922,368, 2024 - Google Patents
Techniques for classifying and processing physical objects are disclosed. In an example, a
computer system may receive first data indicating that a first machine learning model of a …

Hybrid computing achitectures with specialized processors to encode/decode latent representations for controlling dynamic mechanical systems

J Kranski, C Cianci, C Wales, A Kaehler - US Patent 11,691,278, 2023 - Google Patents
Provided is a robot that includes: a first sensor having a first output and configured to sense
state of a robot or an environment of the robot; a first hardware machine-learning accelerator …

Ultra-wide instantaneous bandwidth complex neuromorphic adaptive core processor

S Adl, P Petre, AV Kabakian, BH Fong - US Patent 12,057,989, 2024 - Google Patents
Described is a system for Neuromorphic Adaptive Core (NeurACore) signal processor for
ultra-wide instantaneous bandwidth denoising of a noisy signal. The NeurACore signal …

Robust adaptive dynamic mode decomposition for modeling, prediction, and control of high dimensional physical systems

M Benosman, S Nabi - US Patent 11,790,247, 2023 - Google Patents
A computer-implemented method is provided. The computer-implemented includes a data-
driven model and a robust closure model stored in a memory by using a processor for …

True Positive Transplant

IPM Bataller, PC Leger, A Greenberg - US Patent App. 17/657,464, 2022 - Google Patents
Abstract Systems and methods for augmenting a data set are provided. An example method
may include locating a foreground object disposed within a seed image, identifying an …

End-to-end neural compression with deep reinforcement learning

W Jiang, W Wang, S Lin, S Liu - US Patent 11,917,154, 2024 - Google Patents
End-to-end neural image compression using deep reinforcement learning (DRL) is
performed by at least one processor and includes encoding an input, generating encoded …

Load balancing using data-efficient learning

D Wu, J Kang, H Li, X Chen, YT Xu… - US Patent App. 17 …, 2022 - Google Patents
Rapid and data-efficient training of an artificial intelligence (AI) algorithm are disclosed.
Ground truth data are not available and a policy must be learned based on limited …